ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Super Resolution Using a Single Image Dictionary

Ramakanth, Avinash S and Babu, Venkatesh R (2014) Super Resolution Using a Single Image Dictionary. In: 2014 IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTING AND COMMUNICATION TECHNOLOGIES (IEEE CONECCT) .

[img] PDF
iee_int_con_ele_com_com_tec_2014.pdf - Published Version
Restricted to Registered users only

Download (3967Kb) | Request a copy

Abstract

To perform super resolution of low resolution images, state-of-the-art methods are based on learning a pair of lowresolution and high-resolution dictionaries from multiple images. These trained dictionaries are used to replace patches in lowresolution image with appropriate matching patches from the high-resolution dictionary. In this paper we propose using a single common image as dictionary, in conjunction with approximate nearest neighbour fields (ANNF) to perform super resolution (SR). By using a common source image, we are able to bypass the learning phase and also able to reduce the dictionary from a collection of hundreds of images to a single image. By adapting recent developments in ANNF computation, to suit super-resolution, we are able to perform much faster and accurate SR than existing techniques. To establish this claim, we compare the proposed algorithm against various state-of-the-art algorithms, and show that we are able to achieve b etter and faster reconstruction without any training.

Item Type: Journal Article
Related URLs:
Additional Information: Copy right for this article belongs to the IEEE International Conference on Electronics, Computing and Communication Technologies (IEEE CONECCT), Indian Inst Sci, Bangalore, INDIA, JAN 06-07, 2014
Keywords: Super Resolution; PatchMatch; Synthetic Images; Approximate Nearest Neighbour Field
Department/Centre: Division of Information Sciences > Supercomputer Education & Research Centre
Date Deposited: 01 Apr 2015 12:16
Last Modified: 01 Apr 2015 12:16
URI: http://eprints.iisc.ernet.in/id/eprint/51168

Actions (login required)

View Item View Item